{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T10:57:15Z","timestamp":1772881035539,"version":"3.50.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030695347","type":"print"},{"value":"9783030695354","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69535-4_16","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:13:11Z","timestamp":1614179591000},"page":"257-272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Spotting: Deep Reinforcement Object Search in 3D Point Clouds"],"prefix":"10.1007","author":[{"given":"Onkar","family":"Krishna","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Go","family":"Irie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaomeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahito","family":"Kawanishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunio","family":"Kashino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"16_CR1","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedeings of CVPR, pp. 77\u201385 (2017)"},{"key":"16_CR2","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of NeurIPS, pp. 5099\u20135108 (2017)"},{"key":"16_CR3","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: convolution on X-transformed points. In: Proceedings of NeurIPS, pp. 828\u2013838 (2018)"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum PointNets for 3D object detection from RGB-D data. In: Proceedings of CVPR, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Xu, D., Anguelov, D., Jain, A.: PointFusion: deep sensor fusion for 3D bounding box estimation. In: Proceedings of CVPR, pp. 244\u2013253 (2018)","DOI":"10.1109\/CVPR.2018.00033"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: Proceedings of CVPR, pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3D object detection in point clouds. In: Proceedings of ICCV, pp. 9276\u20139285 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Du, L., et al.: Associate-3Ddet: perceptual-to-conceptual association for 3D point cloud object detection. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01334"},{"key":"16_CR9","unstructured":"Pham, Q.H., et al.: RGB-D object-to-CAD retrieval. In: Proceedings of Eurographics Workshop on 3D Object Retrieval, pp. 45\u201352 (2018)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Uy, M.A., Lee, G.H.: PointNetVLAD: deep point cloud based retrieval for large-scale place recognition. In: Proceedings of CVPR, pp. 4470\u20134479 (2018)","DOI":"10.1109\/CVPR.2018.00470"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, W., Xiao, C.: PCAN: 3D attention map learning using contextual information for point cloud based retrieval. In: Proceedings of CVPR, pp. 12436\u201312445 (2019)","DOI":"10.1109\/CVPR.2019.01272"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Maturana, D., Scherer, S.A.: VoxNet: a 3D convolutional neural network for real-time object recognition. In: Proceedings of IROS, pp. 922\u2013928 (2015)","DOI":"10.1109\/IROS.2015.7353481"},{"key":"16_CR13","unstructured":"Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes. In: Proceedings of CVPR, pp. 1912\u20131920 (2015)"},{"key":"16_CR14","unstructured":"Wang, D.Z., Posner, I.: Voting for voting in online point cloud object detection. In: Proceedings of Robotics: Science and Systems (2015)"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Riegler, G., Ulusoy, A.O., Geiger, A.: OctNet: learning deep 3D representations at high resolutions. In: Proceedings of CVPR, pp. 6620\u20136629 (2017)","DOI":"10.1109\/CVPR.2017.701"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Engelcke, M., Rao, D., Wang, D.Z., Tong, C.H., Posner, I.: Vote3Deep: fast object detection in 3D point clouds using efficient convolutional neural networks. In: Proceedings of ICRA, pp. 1355\u20131361 (2017)","DOI":"10.1109\/ICRA.2017.7989161"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Le, T., Duan, Y.: PointGrid: a deep network for 3D shape understanding. In: Proceedings of CVPR, pp. 9204\u20139214 (2018)","DOI":"10.1109\/CVPR.2018.00959"},{"key":"16_CR18","unstructured":"Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3D shape recognition. In: Proc. ICCV. (2015) 945\u2013953"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Su, H., Nie\u00dfner, M., Dai, A., Yan, M., Guibas, L.J.: Volumetric and multi-view CNNs for object classification on 3D data. In: Proceedings of CVPR, pp. 5648\u20135656 (2016)","DOI":"10.1109\/CVPR.2016.609"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Bai, S., Bai, X., Zhou, Z., Zhang, Z., Jan Latecki, L.: GIFT: a real-time and scalable 3D shape search engine. In: Proceedings of CVPR, pp. 5023\u20135032 (2016)","DOI":"10.1109\/CVPR.2016.543"},{"key":"16_CR21","unstructured":"Savva, M., et al.: Large-scale 3D shape retrieval from ShapeNet Core55. In: Proceedings of Eurographics Workshop on 3D Object Retrieval (2016)"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, B.M., Lee, G.H.: SO-net: self-organizing network for point cloud analysis. In: Proceedings of CVPR, pp. 9397\u20139406 (2018)","DOI":"10.1109\/CVPR.2018.00979"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Hua, B.S., Tran, M.K., Yeung, S.K.: Pointwise convolutional neural networks. In: Proceedings of CVPR, pp. 984\u2013993 (2018)","DOI":"10.1109\/CVPR.2018.00109"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Tatarchenko, M., Park, J., Koltun, V., Zhou, Q.Y.: Tangent convolutions for dense prediction in 3D. In: Proceedings of CVPR, pp. 3887\u20133896 (2018)","DOI":"10.1109\/CVPR.2018.00409"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Wu, W., Qi, Z., Li, F.: PointConv: deep convolutional networks on 3D point clouds. In: Proceedings of CVPR, pp. 9621\u20139630 (2019)","DOI":"10.1109\/CVPR.2019.00985"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Qi, X., Liao, R., Jia, J., Fidler, S., Urtasun, R.: 3D graph neural networks for RGBD semantic segmentation. In: Proceedings of ICCV, pp. 5209\u20135218 (2017)","DOI":"10.1109\/ICCV.2017.556"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Yang, Y., Feng, C., Shen, Y., Tian, D.: FoldingNet: point cloud auto-encoder via deep grid deformation. In: Proceedings of CVPR, pp. 206\u2013215 (2018)","DOI":"10.1109\/CVPR.2018.00029"},{"key":"16_CR28","first-page":"146:1","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. (TOG) 38, 146:1\u2013146:12 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Su, H., et al.: SPLATNet: sparse lattice networks for point cloud processing. In: Proceedings of CVPR, pp. 2530\u20132539 (2018)","DOI":"10.1109\/CVPR.2018.00268"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Rusu, R.B., Blodow, N., Marton, Z.C., Beetz, M.: Aligning point cloud views using persistent feature histograms. In: Proceedings of IROS, pp. 3384\u20133391 (2008)","DOI":"10.1109\/IROS.2008.4650967"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: efficient and robust 3D object recognition. In: Proceedings of CVPR, pp. 998\u20131005 (2010)","DOI":"10.1109\/CVPR.2010.5540108"},{"key":"16_CR32","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.cviu.2014.04.011","volume":"125","author":"S Salti","year":"2014","unstructured":"Salti, S., Tombari, F., Di Stefano, L.: SHOT: unique signatures of histograms for surface and texture description. Comput. Vis. Image Underst. 125, 251\u2013264 (2014)","journal-title":"Comput. Vis. Image Underst."},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Arandjelovic\u0300, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: Proceedings of CVPR, pp. 5297\u20135307 (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Saidi, F., Stasse, O., Yokoi, K., Kanehiro, F.: Online object search with a humanoid robot. In: Proceedings of IROS, pp. 1677\u20131682 (2007)","DOI":"10.1109\/IROS.2007.4399206"},{"key":"16_CR35","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1109\/TRO.2013.2256686","volume":"29","author":"A Aydemir","year":"2013","unstructured":"Aydemir, A., Pronobis, A., Gobelbecker, M., Jensfelt, P.: Active visual object search in unknown environments using uncertain semantics. IEEE Trans. Robot. 29, 986\u20131002 (2013)","journal-title":"IEEE Trans. Robot."},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Searching for objects using structure in indoor scenes. In: Proceedings of BMVC, pp. 53.1\u201353.11 (2015)","DOI":"10.5244\/C.29.53"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Krishna, O., Irie, G., Wu, X., Kawanishi, T., Kashino, K.: Learning search path for region-level image matching. In: Proceedings of ICASSP, pp. 1967\u20131971 (2019)","DOI":"10.1109\/ICASSP.2019.8682714"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, D., Fang, J., Song, X., Guan, C., Yin, J., Dai, Y., Yang, R.: IoU loss for 2D\/3D object detection. In: Proceedings of 3DV, pp. 85\u201394 (2019)","DOI":"10.1109\/3DV.2019.00019"},{"key":"16_CR39","unstructured":"Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: Proceedings of NeurIPS, pp. 2204\u20132212 (2014)"},{"key":"16_CR40","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: Proceedings of ICLR (2015)"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Ablavatski, A., Lu, S., Cai, J.: Enriched deep recurrent visual attention model for multiple object recognition. In: Proceedings of WACV, pp. 971\u2013978 (2017)","DOI":"10.1109\/WACV.2017.113"},{"key":"16_CR42","unstructured":"Armeni, I., Sax, A., Zamir, A.R., Savarese, S.: Joint 2D\u20133D-semantic data for indoor scene understanding. arXiv:1702.01105 (2017)"},{"key":"16_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/978-3-319-73013-4_23","volume-title":"Analysis of Images, Social Networks and Texts","author":"A Notchenko","year":"2018","unstructured":"Notchenko, A., Kapushev, Y., Burnaev, E.: Large-scale shape retrieval with sparse 3d convolutional neural networks. In: van der Aalst, W.M.P., et al. (eds.) AIST 2017. LNCS, vol. 10716, pp. 245\u2013254. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-73013-4_23"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69535-4_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:43:27Z","timestamp":1614181407000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69535-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695347","9783030695354"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69535-4_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"254","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}